Amazon (United States)

The Allen Institute for Brain Science and AWS have released Bloom, a single-cell multimodal model that encodes gene expression and chromatin accessibility into one shared cell representation while training on roughly 100-fold fewer cells than comparable pretrained models. On adult mouse whole-brain data, linear classifiers on Bloom embeddings reach 91% cross-validated adjusted balanced accuracy for 315 subclasses (multiome), 94% for 310 subclasses (scRNA-seq) and 94% for 297 subclasses (snRNA-seq), although the model saw only mouse multiome data.

The Allen Institute for Brain Science and AWS have released Bloom, a single-cell multimodal model that encodes gene expression and chromatin accessibility into one shared cell representation while training on roughly 100-fold fewer cells than comparable pretrained models. On adult mouse whole-brain data, linear classifiers on Bloom embeddings reach 91% cross-validated adjusted balanced accuracy for 315 subclasses (multiome), 94% for 310 subclasses (scRNA-seq) and 94% for 297 subclasses (snRNA-seq), although the model saw only mouse multiome data.

A 35B agentic verifier that sees only the problem statement and a candidate program, never the official tests, uses self-generated counterexamples as executable evidence to raise binary verdict accuracy on USACO-Judge from 71.41% to 87.41%.

A 35B agentic verifier that sees only the problem statement and a candidate program, never the official tests, uses self-generated counterexamples as executable evidence to raise binary verdict accuracy on USACO-Judge from 71.41% to 87.41%.

Everyday humanoid work such as pushing a cart, moving a box or wiping a surface needs controlled contact force, not just tracked hand motion. FLoRe makes force a shared interface across demonstration, policy and whole-body control: two handheld grippers with six-axis force/torque sensors record hand motion and contact wrenches without a robot, a diffusion policy predicts per-hand force commands from those demonstrations, and a whole-body controller tracks them by integrating the measured force error. On a Unitree G1 across three contact-rich tasks, the force-reactive policy succeeded in 80% of rollouts, against 26.7% for a position-only policy trained on the same demonstrations and run by the same controller.

Everyday humanoid work such as pushing a cart, moving a box or wiping a surface needs controlled contact force, not just tracked hand motion. FLoRe makes force a shared interface across demonstration, policy and whole-body control: two handheld grippers with six-axis force/torque sensors record hand motion and contact wrenches without a robot, a diffusion policy predicts per-hand force commands from those demonstrations, and a whole-body controller tracks them by integrating the measured force error. On a Unitree G1 across three contact-rich tasks, the force-reactive policy succeeded in 80% of rollouts, against 26.7% for a position-only policy trained on the same demonstrations and run by the same controller.

Writing tool, resource and execution policies into a task agent's prompt does not reliably prevent violations. AgentPolicyForge uses executable environments to build policy benchmarks and iteratively train policy guards, yielding PolicyGym, which spans ten policy families with 698 scenarios for training-data generation and 254 separate held-out scenarios. On PolicyGym, the final guard-based configuration achieves a 40–44% relative reduction in attack success rate and fewer benign rejections than policy prompting alone.

Writing tool, resource and execution policies into a task agent's prompt does not reliably prevent violations. AgentPolicyForge uses executable environments to build policy benchmarks and iteratively train policy guards, yielding PolicyGym, which spans ten policy families with 698 scenarios for training-data generation and 254 separate held-out scenarios. On PolicyGym, the final guard-based configuration achieves a 40–44% relative reduction in attack success rate and fewer benign rejections than policy prompting alone.

Probabilistic time-series forecasting must capture temporal structure, express uncertainty and infer quickly; diffusion and flow-matching methods buy flexibility with multi-step iterative sampling whose cost grows with the number of steps. KGO treats prediction as the evolution of structured uncertainty in a Koopman latent space: KoPE extrapolates latent trajectories with a learned linear operator, KoFM transports noise to the future in one step via a matrix exponential, and AUG adapts the deterministic and stochastic mix per variable and horizon. Across 17 ProbTS settings, KGO reports the lowest CRPS on 13 and the lowest NMAE on 16, with at least a 25-fold inference speedup over iterative generative models.

Probabilistic time-series forecasting must capture temporal structure, express uncertainty and infer quickly; diffusion and flow-matching methods buy flexibility with multi-step iterative sampling whose cost grows with the number of steps. KGO treats prediction as the evolution of structured uncertainty in a Koopman latent space: KoPE extrapolates latent trajectories with a learned linear operator, KoFM transports noise to the future in one step via a matrix exponential, and AUG adapts the deterministic and stochastic mix per variable and horizon. Across 17 ProbTS settings, KGO reports the lowest CRPS on 13 and the lowest NMAE on 16, with at least a 25-fold inference speedup over iterative generative models.

Distillation no longer treats every teacher token alike: each token's weight is set by its predicted effect on the student's post-update reward. Earlier token-selection methods relied on proxies such as uncertainty or teacher-student divergence, which need not identify reward-improving supervision. RAD scores each token by differentiating through a temporary optimizer step, then updates token weights by projected ascent, improving mean accuracy on six competition-math benchmarks by 6.5 points for Qwen3-1.7B and 2.5 points for Qwen3-4B-Instruct-2507 at a matched training-response budget, and reaching 54.69% and 58.67% pass@1 on LiveCodeBench-v6.

Distillation no longer treats every teacher token alike: each token's weight is set by its predicted effect on the student's post-update reward. Earlier token-selection methods relied on proxies such as uncertainty or teacher-student divergence, which need not identify reward-improving supervision. RAD scores each token by differentiating through a temporary optimizer step, then updates token weights by projected ascent, improving mean accuracy on six competition-math benchmarks by 6.5 points for Qwen3-1.7B and 2.5 points for Qwen3-4B-Instruct-2507 at a matched training-response budget, and reaching 54.69% and 58.67% pass@1 on LiveCodeBench-v6.

Agentic training-data synthesis has a new shape: EvoSyn turns learner feedback into a revisable synthesis space, so what gets generated follows the task agent's weak spots. Earlier methods used environment feedback, data validation, or learner failures, but observed weaknesses did not directly say what the next round should generate, nor whether existing synthesis dimensions could represent them. On τ-Bench and CAR-Bench with Opus 4.5 as the synthesis model, average task success rises from 64.5% for the strongest synthesis baseline to 77.8%, reaching 70.9% after the first round, with multi-round evolution adding further gains.

Agentic training-data synthesis has a new shape: EvoSyn turns learner feedback into a revisable synthesis space, so what gets generated follows the task agent's weak spots. Earlier methods used environment feedback, data validation, or learner failures, but observed weaknesses did not directly say what the next round should generate, nor whether existing synthesis dimensions could represent them. On τ-Bench and CAR-Bench with Opus 4.5 as the synthesis model, average task success rises from 64.5% for the strongest synthesis baseline to 77.8%, reaching 70.9% after the first round, with multi-round evolution adding further gains.

Pretrained dense models can be expanded during continued training instead of pretraining a sparse architecture from scratch. STAPLE keeps the pretrained feed-forward up-projection and adds zero-initialized token-indexed embedding tables as a residual pathway, so the new parameters learn complementary token-specific information. On OLMo-2 1B it raises the ten-task average from 44.39 to 45.59 over continued dense training, with HumanEval up 4.27 points, MBPP 2.80, GSM8K 2.27 and DROP 1.65, and gains persist on OLMo-2 7B.

Pretrained dense models can be expanded during continued training instead of pretraining a sparse architecture from scratch. STAPLE keeps the pretrained feed-forward up-projection and adds zero-initialized token-indexed embedding tables as a residual pathway, so the new parameters learn complementary token-specific information. On OLMo-2 1B it raises the ten-task average from 44.39 to 45.59 over continued dense training, with HumanEval up 4.27 points, MBPP 2.80, GSM8K 2.27 and DROP 1.65, and gains persist on OLMo-2 7B.

EvoBelief writes an agent's knowledge of its environment as falsifiable hypotheses, and only rules that survive independent evidence may change predictions or plans, while the language model stays frozen. On ALFWorld without actor-side transition memory it raises success over the matched Frozen World Model by 23.9% with Claude Haiku 4.5 and 31.3% with GPT-5.4; in DiscoveryWorld's Reactor Lab it completes 83.3% of Normal-tier and 58.3% of Challenge-tier instances, versus 0% for each evaluated baseline.

EvoBelief writes an agent's knowledge of its environment as falsifiable hypotheses, and only rules that survive independent evidence may change predictions or plans, while the language model stays frozen. On ALFWorld without actor-side transition memory it raises success over the matched Frozen World Model by 23.9% with Claude Haiku 4.5 and 31.3% with GPT-5.4; in DiscoveryWorld's Reactor Lab it completes 83.3% of Normal-tier and 58.3% of Challenge-tier instances, versus 0% for each evaluated baseline.

The work recasts conversational query rewriting as a sequential retrieval problem in which an agent chooses among intent resolution, lexical reformulation, and pseudo-document synthesis, conditioning each rewrite on passages returned by the previous step, and is trained by supervised fine-tuning plus reinforcement learning against retrieval quality alone with no human rewrite annotations; it achieves the highest MRR and NDCG@3 on TopiOCQA and QReCC and transfers zero-shot to TREC CAsT and to dense retrieval backends.

The work recasts conversational query rewriting as a sequential retrieval problem in which an agent chooses among intent resolution, lexical reformulation, and pseudo-document synthesis, conditioning each rewrite on passages returned by the previous step, and is trained by supervised fine-tuning plus reinforcement learning against retrieval quality alone with no human rewrite annotations; it achieves the highest MRR and NDCG@3 on TopiOCQA and QReCC and transfers zero-shot to TREC CAsT and to dense retrieval backends.